© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 670
    Prev
    Next
    INDEX
    Explanations

    countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McCle
    1.36
    ytuc
    1.29
    堤
    1.22
     encima
    1.22
    мас
    1.22
    orns
    1.21
    şam
    1.20
    茆
    1.19
    loz
    1.19
    χαν
    1.19
    POSITIVE LOGITS
     Italy
    3.13
     Germany
    3.10
     France
    3.10
     Australia
    3.06
     Sweden
    3.00
     Europe
    2.99
     Belgium
    2.98
    Italy
    2.98
     Japan
    2.98
     England
    2.94
    Activations Density 5.335%

    No Known Activations